One JSON UI prompt, three tools: ChatGPT vs Claude vs Figma Make design showdown
Tegadesigns · x · 2026-10-06
Designer Tegadesigns ran the same structured JSON prompt through ChatGPT, Claude, and Figma Make to generate a music streaming app home screen, inviting people to pick the winner.
Reusable prompt structure: break the screen into fields — screen (page type), device (iPhone 15 Pro, 393x852, status bar at 9:41), mode (light), style (modern, minimal, image-led, generous spacing), typography (Inter, headings 600 / body 400), colors (background #F4F4F1, cards #FFFFFF, brand #D4F06B), and layout (block-by-block specs for avatar, greeting, filter chips, and banner composition and copy placement).
Field-based prompts like this make design/image models far more controllable and closer to production-ready mockups — handy for designers and front-end engineers.
Related event: Designer Benchmarks ChatGPT, Claude and Figma Make With Same Prompt(3 posts)→
More from Multimodal
- AssemblyAI's Universal 3.6 Pro cuts voice-agent transcription errors 45%, adds 14 languages — AssemblyAI · 2026-10-06
- Open-source fibo-scene-analyzer outputs structured captions, bboxes and poses in one model — linoy_tsaban · 2026-10-06
- VibeEditing first try: a single prompt produces a decent video edit with HyperFrames — toolstelegraph · 2026-10-06
- RTX 5080 vs 5060 Ti benchmarked on FLUX Krea 2: 2.1x faster, wildly asymmetric LoRA penalty — Altruistic_Print717 · 2026-10-06
- Hedra Multiplayer launches: shared canvas where each teammate works with their own agent — henloitsjoyce · 2026-10-06
- Reka AI's 19B omni-model Rho-1 handles text, images, video and robot control in one net — The Decoder · 2026-10-06